llama-stack-mirror/tests/unit/providers/agents
Ben Browning badf8594d1 feat: Structured output for Responses API
This adds the missing `text` parameter to the Responses API that is
how users control structured outputs. All we do with that parameter is
map it to the corresponding chat completion response_format.

The unit tests exercise the various permutations allowed for this
property, while a couple of new verification tests actually use it for
real to verify the model outputs are following the format as expected.

Signed-off-by: Ben Browning <bbrownin@redhat.com>
2025-06-02 19:43:40 -04:00
..
meta_reference feat: Structured output for Responses API 2025-06-02 19:43:40 -04:00
test_persistence_access_control.py feat: implementation for agent/session list and describe (#1606) 2025-05-07 14:49:23 +02:00